Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.04182 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915478989963264 |
|---|---|
| author | Liu, Wei Strube, Michael |
| author_facet | Liu, Wei Strube, Michael |
| contents | In linguistics, coherence can be achieved by different means, such as by maintaining reference to the same set of entities across sentences and by establishing discourse relations between them. However, most existing work on coherence modeling focuses exclusively on either entity features or discourse relation features, with little attention given to combining the two. In this study, we explore two methods for jointly modeling entities and discourse relations for coherence assessment. Experiments on three benchmark datasets show that integrating both types of features significantly enhances the performance of coherence models, highlighting the benefits of modeling both simultaneously for coherence evaluation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_04182 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Joint Modeling of Entities and Discourse Relations for Coherence Assessment Liu, Wei Strube, Michael Computation and Language In linguistics, coherence can be achieved by different means, such as by maintaining reference to the same set of entities across sentences and by establishing discourse relations between them. However, most existing work on coherence modeling focuses exclusively on either entity features or discourse relation features, with little attention given to combining the two. In this study, we explore two methods for jointly modeling entities and discourse relations for coherence assessment. Experiments on three benchmark datasets show that integrating both types of features significantly enhances the performance of coherence models, highlighting the benefits of modeling both simultaneously for coherence evaluation. |
| title | Joint Modeling of Entities and Discourse Relations for Coherence Assessment |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.04182 |